# Installing the libraries with the specified version.
!pip install pandas==1.5.3 numpy==1.25.2 matplotlib==3.7.1 seaborn==0.13.1 scikit-learn==1.2.2 statsmodels==0.14.1 -q --user

# Libraries to help with reading and manipulating data
import pandas as pd
import numpy as np

# libaries to help with data visualization
import matplotlib.pyplot as plt
import seaborn as sns

# Removes the limit for the number of displayed columns
pd.set_option("display.max_columns", None)
# Sets the limit for the number of displayed rows
pd.set_option("display.max_rows", 200)
# setting the precision of floating numbers to 5 decimal points
pd.set_option("display.float_format", lambda x: "%.5f" % x)

# Library to split data
from sklearn.model_selection import train_test_split

# To build model for prediction
import statsmodels.stats.api as sms
from statsmodels.stats.outliers_influence import variance_inflation_factor
import statsmodels.api as sm
from statsmodels.tools.tools import add_constant
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree

# To tune different models
from sklearn.model_selection import GridSearchCV


# To get diferent metric scores
from sklearn.metrics import (
    f1_score,
    accuracy_score,
    recall_score,
    precision_score,
    confusion_matrix,
    roc_auc_score,
    precision_recall_curve,
    roc_curve,
    make_scorer,
)

import warnings
warnings.filterwarnings("ignore")

from statsmodels.tools.sm_exceptions import ConvergenceWarning
warnings.simplefilter("ignore", ConvergenceWarning)

# uncomment and run the following lines for Google Colab
# from google.colab import drive
# drive.mount('/content/drive')

# Code to let colab access my google drive
from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive

# Code to read dataset
hotel = pd.read_csv('/content/drive/My Drive/INNHotelsGroup.csv')

# copying data to another variable to avoid any changes to original data
data = hotel.copy()

# Code to view the first 5 rows of the dataset
data.head()

# Code to view the last 5 rows of the dataset
data.tail()

# Code to check the shape of the dataset
data.shape
print('There are', data.shape[0],'rows and', data.shape[1],'columns')

There are 36275 rows and 19 columns

# Code to determine datatypes of different columns in the dataset
info = data.info()
print(info)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 36275 entries, 0 to 36274
Data columns (total 19 columns):
 #   Column                                Non-Null Count  Dtype  
---  ------                                --------------  -----  
 0   Booking_ID                            36275 non-null  object 
 1   no_of_adults                          36275 non-null  int64  
 2   no_of_children                        36275 non-null  int64  
 3   no_of_weekend_nights                  36275 non-null  int64  
 4   no_of_week_nights                     36275 non-null  int64  
 5   type_of_meal_plan                     36275 non-null  object 
 6   required_car_parking_space            36275 non-null  int64  
 7   room_type_reserved                    36275 non-null  object 
 8   lead_time                             36275 non-null  int64  
 9   arrival_year                          36275 non-null  int64  
 10  arrival_month                         36275 non-null  int64  
 11  arrival_date                          36275 non-null  int64  
 12  market_segment_type                   36275 non-null  object 
 13  repeated_guest                        36275 non-null  int64  
 14  no_of_previous_cancellations          36275 non-null  int64  
 15  no_of_previous_bookings_not_canceled  36275 non-null  int64  
 16  avg_price_per_room                    36275 non-null  float64
 17  no_of_special_requests                36275 non-null  int64  
 18  booking_status                        36275 non-null  object 
dtypes: float64(1), int64(13), object(5)
memory usage: 5.3+ MB
None

# Code to check the statistical summary of dataset
data.describe().T

# Code to check missing values in the dataset
data.isnull().sum()

# Code to check for duplicates
data.duplicated().sum()

0

#Code to drop Booking-ID so we can proceed
data.drop('Booking_ID',axis=1,inplace=True)

data.head()

def histogram_boxplot(data, feature, figsize=(15, 10), kde=False, bins=None):
    """
    Boxplot and histogram combined

    data: dataframe
    feature: dataframe column
    figsize: size of figure (default (15,10))
    kde: whether to show the density curve (default False)
    bins: number of bins for histogram (default None)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows=2,  # Number of rows of the subplot grid= 2
        sharex=True,  # x-axis will be shared among all subplots
        gridspec_kw={"height_ratios": (0.25, 0.75)},
        figsize=figsize,
    )  # creating the 2 subplots
    sns.boxplot(
        data=data, x=feature, ax=ax_box2, showmeans=True, color="violet"
    )  # boxplot will be created and a triangle will indicate the mean value of the column
    sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2, bins=bins
    ) if bins else sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2
    )  # For histogram
    ax_hist2.axvline(
        data[feature].mean(), color="green", linestyle="--"
    )  # Add mean to the histogram
    ax_hist2.axvline(
        data[feature].median(), color="black", linestyle="-"
    )  # Add median to the histogram

def labeled_barplot(data, feature, perc=False, n=None):
       """
       Barplot with percentage labels.

       data: dataframe
       feature: dataframe column
       perc: whether to display percentages instead of counts (default False)
       n: number of bars to display (default None, displays all bars)
       """
       total = len(data[feature])  # length of the column
       count = data[feature].nunique()
       if n is None:
           plt.figure(figsize=(count + 1, 5))
       else:
           plt.figure(figsize=(n + 1, 5))

       plt.xticks(rotation=90, fontsize=15)
       ax = sns.countplot(
           data=data,
           x=feature,
           order=data[feature].value_counts().index[:n].sort_values(),
           palette="Set2",
       )

       for p in ax.patches:
           if perc == True:
               label = "{:.1f}%".format(
                   100 * p.get_height() / total
               )  # percentage of each class of the category

labeled_barplot(data, "no_of_adults", perc=True)

data['no_of_adults'].unique()

array([2, 1, 3, 0, 4])

def get_bookings_by_adults(data, num_adults):
  """
  Gets the number of bookings for a given number of adults.

  Args:
    data: The pandas DataFrame containing booking data.
    num_adults: The number of adults to filter by.

  Returns:
    The number of bookings with the specified number of adults.
  """
  bookings_for_adults = data[data['no_of_adults'] == num_adults]
  num_bookings = bookings_for_adults.shape[0]
  return num_bookings

# Get bookings for different adult counts
adult_counts = [0, 1, 2, 3, 4]
for num_adults in adult_counts:
  num_bookings = get_bookings_by_adults(data, num_adults)
  print(f"Number of bookings for {num_adults} adult(s): {num_bookings}")

Number of bookings for 0 adult(s): 139
Number of bookings for 1 adult(s): 7695
Number of bookings for 2 adult(s): 26108
Number of bookings for 3 adult(s): 2317
Number of bookings for 4 adult(s): 16

labeled_barplot(data, "no_of_children", perc=True)  ## Complete the code to create labeled_barplot for number of children

# replacing 9, and 10 children with 3
data["no_of_children"] = data["no_of_children"].replace([9, 10], 3)

def get_bookings_by_children(data, num_children):
  """
  Gets the number of bookings for a given number of children.

  Args:
    data: The pandas DataFrame containing booking data.
    num_children: The number of children to filter by.

  Returns:
    The number of bookings with the specified number of children.
  """
  bookings_for_children = data[data['no_of_children'] == num_children]
  num_bookings = bookings_for_children.shape[0]
  return num_bookings

# Get bookings for different children counts
children_counts = [0, 1, 2, 3, 4]
for num_children in children_counts:
  num_bookings = get_bookings_by_children(data, num_children)
  print(f"Number of bookings for {num_children} child(ren): {num_bookings}")

Number of bookings for 0 child(ren): 33577
Number of bookings for 1 child(ren): 1618
Number of bookings for 2 child(ren): 1058
Number of bookings for 3 child(ren): 22
Number of bookings for 4 child(ren): 0

labeled_barplot(data,'no_of_weekend_nights')

def get_bookings_by_weekend_nights(data, num_nights):
  """
  Gets the number of bookings for a given number of weekend nights.

  Args:
    data: The pandas DataFrame containing booking data.
    num_nights: The number of weekend nights to filter by.

  Returns:
    The number of bookings with the specified number of weekend nights.
  """
  bookings_for_nights = data[data['no_of_weekend_nights'] == num_nights]
  num_bookings = bookings_for_nights.shape[0]
  return num_bookings

# Get bookings for different weekend night counts
weekend_night_counts = [0, 1, 2, 3, 4, 5, 6, 7]
for num_nights in weekend_night_counts:
  num_bookings = get_bookings_by_weekend_nights(data, num_nights)
  print(f"Number of bookings for {num_nights} weekend night(s): {num_bookings}")

Number of bookings for 0 weekend night(s): 16872
Number of bookings for 1 weekend night(s): 9995
Number of bookings for 2 weekend night(s): 9071
Number of bookings for 3 weekend night(s): 153
Number of bookings for 4 weekend night(s): 129
Number of bookings for 5 weekend night(s): 34
Number of bookings for 6 weekend night(s): 20
Number of bookings for 7 weekend night(s): 1

labeled_barplot(data,'no_of_week_nights')

# Filter bookings with more than 5 weeknights
filtered_bookings = data[data['no_of_week_nights'] > 5]

# Count filtered bookings
num_filtered_bookings = filtered_bookings.shape[0]

# Calculate the percentage
percentage = (num_filtered_bookings / data.shape[0]) * 100

# Print the result
print(f"Percentage of bookings extending beyond 5 weeknights: {percentage:.2f}%")

Percentage of bookings extending beyond 5 weeknights: 1.41%

labeled_barplot(data,'type_of_meal_plan')

labeled_barplot(data,'required_car_parking_space')

total_parking_required = data['required_car_parking_space'].sum()

print(f"Total car parking spaces required: {total_parking_required}")

Total car parking spaces required: 1124

labeled_barplot(data,'room_type_reserved')

def calculate_room_type_percentages(data):
  """
  Calculates the percentage of reservations for each room type.

  Args:
    data: The pandas DataFrame containing booking data.

  Returns:
    A pandas Series containing the percentage of reservations for each room type.
  """
  room_type_counts = data['room_type_reserved'].value_counts()
  total_bookings = data.shape[0]
  room_type_percentages = (room_type_counts / total_bookings) * 100
  return room_type_percentages

# Calculate and print the percentages
room_type_percentages = calculate_room_type_percentages(data)
print(room_type_percentages)

room_type_reserved
Room_Type 1   77.54652
Room_Type 4   16.69745
Room_Type 6    2.66299
Room_Type 2    1.90765
Room_Type 5    0.73053
Room_Type 7    0.43556
Room_Type 3    0.01930
Name: count, dtype: float64

histogram_boxplot(data, "lead_time") # Code to plot histogram and boxplot

labeled_barplot(data,'arrival_year')

def calculate_arrival_year_percentages(data):
  """
  Calculates the percentage of bookings for each arrival year.

  Args:
    data: The pandas DataFrame containing booking data.

  Returns:
    A pandas Series containing the percentage of bookings for each arrival year.
  """
  arrival_year_counts = data['arrival_year'].value_counts()
  total_bookings = data.shape[0]
  arrival_year_percentages = (arrival_year_counts / total_bookings) * 100
  return arrival_year_percentages

# Calculate and print the percentages
arrival_year_percentages = calculate_arrival_year_percentages(data)
print(arrival_year_percentages)

arrival_year
2018   82.04273
2017   17.95727
Name: count, dtype: float64

labeled_barplot(data,'arrival_month')

def calculate_arrival_month_percentages(data):
  """
  Calculates the percentage of bookings for each arrival month.

  Args:
    data: The pandas DataFrame containing booking data.

  Returns:
    A pandas Series containing the percentage of bookings for each arrival month.
  """
  arrival_month_counts = data['arrival_month'].value_counts()
  total_bookings = data.shape[0]
  arrival_month_percentages = (arrival_month_counts / total_bookings) * 100
  return arrival_month_percentages

# Calculate and print the percentages
arrival_month_percentages = calculate_arrival_month_percentages(data)
print(arrival_month_percentages)

arrival_month
10   14.65748
9    12.71123
8    10.51137
6     8.82977
12    8.32805
11    8.21502
7     8.04962
4     7.54238
5     7.16196
3     6.50034
2     4.69745
1     2.79531
Name: count, dtype: float64

labeled_barplot(data,'market_segment_type')

def calculate_market_segment_percentages(data):
  """
  Calculates the percentage of bookings for each market segment type.

  Args:
    data: The pandas DataFrame containing booking data.

  Returns:
    A pandas Series containing the percentage of bookings for each market segment type.
  """
  market_segment_counts = data['market_segment_type'].value_counts()
  total_bookings = data.shape[0]
  market_segment_percentages = (market_segment_counts / total_bookings) * 100
  return market_segment_percentages

# Calculate and print the percentages
market_segment_percentages = calculate_market_segment_percentages(data)
print(market_segment_percentages)

market_segment_type
Online          63.99449
Offline         29.02274
Corporate        5.56030
Complementary    1.07788
Aviation         0.34459
Name: count, dtype: float64

labeled_barplot(data,'repeated_guest') # Code to determine repeated guest

repeated_guest_percentage = (data['repeated_guest'].sum() / len(data)) * 100

print(f"Percentage of repeated guests: {repeated_guest_percentage:.2f}%")

Percentage of repeated guests: 2.56%

labeled_barplot(data,'no_of_previous_cancellations') # Code to visualize number of previous cancellations

# Percentage of bookings with previous cancellations
bookings_with_previous_cancellations = data[data['no_of_previous_cancellations'] > 0]
percentage_with_previous_cancellations = (len(bookings_with_previous_cancellations) / len(data)) * 100
print(f"Percentage of bookings with previous cancellations: {percentage_with_previous_cancellations:.2f}%")

# Percentage of bookings with NO previous cancellations
bookings_with_no_previous_cancellations = data[data['no_of_previous_cancellations'] == 0]
percentage_with_no_previous_cancellations = (len(bookings_with_no_previous_cancellations) / len(data)) * 100
print(f"Percentage of bookings with NO previous cancellations: {percentage_with_no_previous_cancellations:.2f}%")

Percentage of bookings with previous cancellations: 0.93%
Percentage of bookings with NO previous cancellations: 99.07%

histogram_boxplot(data,'no_of_previous_bookings_not_canceled') # Code to create histogram and boxplot

# function to create labeled barplots


def labeled_barplot(data, feature, perc=False, n=None):
    """
    Barplot with percentage at the top

    data: dataframe
    feature: dataframe column
    perc: whether to display percentages instead of count (default is False)
    n: displays the top n category levels (default is None, i.e., display all levels)
    """

    total = len(data[feature])  # length of the column
    count = data[feature].nunique()
    if n is None:
        plt.figure(figsize=(count + 2, 6))
    else:
        plt.figure(figsize=(n + 2, 6))

    plt.xticks(rotation=90, fontsize=15)
    ax = sns.countplot(
        data=data,
        x=feature,
        order=data[feature].value_counts().index[:n],
    )

    for p in ax.patches:
        if perc == True:
            label = "{:.1f}%".format(
                100 * p.get_height() / total
            )  # percentage of each class of the category
        else:
            label = p.get_height()  # count of each level of the category

        x = p.get_x() + p.get_width() / 2  # width of the plot
        y = p.get_height()  # height of the plot

        ax.annotate(
            label,
            (x, y),
            ha="center",
            va="center",
            size=12,
            xytext=(0, 5),
            textcoords="offset points",
        )  # annotate the percentage

    plt.show()  # show the plot

histogram_boxplot(data,'avg_price_per_room')  ## Code to create histogram_boxplot for average price per room

data[data["avg_price_per_room"] == 0]

data.loc[data["avg_price_per_room"] == 0, "market_segment_type"].value_counts()

# Calculating the 25th quantile
Q1 = data["avg_price_per_room"].quantile(0.25) ## Code to calculate 25th quantile for average price per room

# Calculating the 75th quantile
Q3 = data["avg_price_per_room"].quantile(0.75)  ## Code to calculate 75th quantile for average price per room

# Calculating IQR
IQR = Q3 - Q1

# Calculating value of upper whisker
Upper_Whisker = Q3 + 1.5 * IQR
Upper_Whisker

179.55

# assigning the outliers the value of upper whisker
data.loc[data["avg_price_per_room"] >= 500, "avg_price_per_room"] = Upper_Whisker

avg_price = data['avg_price_per_room'].mean()
print(f"The average price of bookings is: {avg_price:.2f} euros")

The average price of bookings is: 103.41 euros

labeled_barplot(data,'no_of_special_requests')  ## Code to create labeled_barplot for number of special requests

labeled_barplot(data,'booking_status')  ## Code to create labeled_barplot for booking status

data["booking_status"] = data["booking_status"].apply(
    lambda x: 1 if x == "Canceled" else 0
)

cols_list = data.select_dtypes(include=np.number).columns.tolist()

plt.figure(figsize=(12, 7))
sns.heatmap(
    data[cols_list].corr(), annot=True, vmin=-1, vmax=1, fmt=".2f", cmap="Spectral"
)
plt.show()

### function to plot distributions wrt target


def distribution_plot_wrt_target(data, predictor, target):

    fig, axs = plt.subplots(2, 2, figsize=(12, 10))

    target_uniq = data[target].unique()

    axs[0, 0].set_title("Distribution of target for target=" + str(target_uniq[0]))
    sns.histplot(
        data=data[data[target] == target_uniq[0]],
        x=predictor,
        kde=True,
        ax=axs[0, 0],
        color="teal",
        stat="density",
    )

    axs[0, 1].set_title("Distribution of target for target=" + str(target_uniq[1]))
    sns.histplot(
        data=data[data[target] == target_uniq[1]],
        x=predictor,
        kde=True,
        ax=axs[0, 1],
        color="orange",
        stat="density",
    )

    axs[1, 0].set_title("Boxplot w.r.t target")
    sns.boxplot(data=data, x=target, y=predictor, ax=axs[1, 0])

    axs[1, 1].set_title("Boxplot (without outliers) w.r.t target")
    sns.boxplot(
        data=data,
        x=target,
        y=predictor,
        ax=axs[1, 1],
        showfliers=False,
    )

    plt.tight_layout()
    plt.show()

# function to plot stacked bar chart


def stacked_barplot(data, predictor, target):
    """
    Print the category counts and plot a stacked bar chart

    data: dataframe
    predictor: independent variable
    target: target variable
    """
    count = data[predictor].nunique()
    sorter = data[target].value_counts().index[-1]
    tab1 = pd.crosstab(data[predictor], data[target], margins=True).sort_values(
        by=sorter, ascending=False
    )
    print(tab1)
    print("-" * 120)
    tab = pd.crosstab(data[predictor], data[target], normalize="index").sort_values(
        by=sorter, ascending=False
    )
    tab.plot(kind="bar", stacked=True, figsize=(count + 5, 6))
    plt.legend(
        loc="lower left", frameon=False,
    )
    plt.legend(loc="upper left", bbox_to_anchor=(1, 1))
    plt.show()

stacked_barplot(
    data,"no_of_adults", "booking_status"
)  # creates stacked barplot of booking status with respect to number of adults

booking_status      0      1    All
no_of_adults                       
All             24390  11885  36275
2               16989   9119  26108
1                5839   1856   7695
3                1454    863   2317
0                  95     44    139
4                  13      3     16
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"no_of_children", "booking_status"
)  # creates stacked barplot of booking status with respect to number of children

booking_status      0      1    All
no_of_children                     
All             24390  11885  36275
0               22695  10882  33577
1                1078    540   1618
2                 601    457   1058
3                  16      6     22
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"no_of_weekend_nights", "booking_status"
)  # Code to create stacked barplot of booking status with respect to number of weekend nights

booking_status            0      1    All
no_of_weekend_nights                     
All                   24390  11885  36275
0                     11779   5093  16872
1                      6563   3432   9995
2                      5914   3157   9071
4                        46     83    129
3                        79     74    153
5                         5     29     34
6                         4     16     20
7                         0      1      1
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"no_of_week_nights", "booking_status"
)  # Code to create stacked barplot of booking status with respect to number of week nights

booking_status         0      1    All
no_of_week_nights                     
All                24390  11885  36275
2                   7447   3997  11444
3                   5265   2574   7839
1                   6916   2572   9488
4                   1847   1143   2990
0                   1708    679   2387
5                    982    632   1614
6                    101     88    189
10                     9     53     62
7                     61     52    113
8                     30     32     62
9                     13     21     34
11                     3     14     17
15                     2      8     10
12                     2      7      9
13                     0      5      5
14                     3      4      7
16                     0      2      2
17                     1      2      3
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"type_of_meal_plan", "booking_status"
)  # Code to create stacked barplot of booking status with respect to type of meal plan

booking_status         0      1    All
type_of_meal_plan                     
All                24390  11885  36275
Meal Plan 1        19156   8679  27835
Not Selected        3431   1699   5130
Meal Plan 2         1799   1506   3305
Meal Plan 3            4      1      5
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"required_car_parking_space", "booking_status"
)  # Code to create stacked barplot of booking status with respect to required car parking space

booking_status                  0      1    All
required_car_parking_space                     
All                         24390  11885  36275
0                           23380  11771  35151
1                            1010    114   1124
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"room_type_reserved", "booking_status"
)  # Code to create stacked barplot of booking status with respect to room type reserved

booking_status          0      1    All
room_type_reserved                     
All                 24390  11885  36275
Room_Type 1         19058   9072  28130
Room_Type 4          3988   2069   6057
Room_Type 6           560    406    966
Room_Type 2           464    228    692
Room_Type 5           193     72    265
Room_Type 7           122     36    158
Room_Type 3             5      2      7
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"arrival_year", "booking_status"
)  # Code to create stacked barplot of booking status with respect to arrival year

booking_status      0      1    All
arrival_year                       
All             24390  11885  36275
2018            18837  10924  29761
2017             5553    961   6514
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"arrival_month", "booking_status"
)  # Code to create stacked barplot of booking status with respect to arrival month

booking_status      0      1    All
arrival_month                      
All             24390  11885  36275
10               3437   1880   5317
9                3073   1538   4611
8                2325   1488   3813
7                1606   1314   2920
6                1912   1291   3203
4                1741    995   2736
5                1650    948   2598
11               2105    875   2980
3                1658    700   2358
2                1274    430   1704
12               2619    402   3021
1                 990     24   1014
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"market_segment_type", "booking_status"
)  # Code to create stacked barplot of booking status with respect to market segment type

booking_status           0      1    All
market_segment_type                     
All                  24390  11885  36275
Online               14739   8475  23214
Offline               7375   3153  10528
Corporate             1797    220   2017
Aviation                88     37    125
Complementary          391      0    391
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"repeated_guest", "booking_status"
)  # Code to create stacked barplot of booking status with respect to repeated guest

booking_status      0      1    All
repeated_guest                     
All             24390  11885  36275
0               23476  11869  35345
1                 914     16    930
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"no_of_previous_cancellations", "booking_status"
)  # Code to create stacked barplot of booking status with respect to no. of previous cancellations

booking_status                    0      1    All
no_of_previous_cancellations                     
All                           24390  11885  36275
0                             24068  11869  35937
1                               187     11    198
13                                0      4      4
3                                42      1     43
2                                46      0     46
4                                10      0     10
5                                11      0     11
6                                 1      0      1
11                               25      0     25
------------------------------------------------------------------------------------------------------------------------

stacked_barplot(
    data,"no_of_previous_bookings_not_canceled", "booking_status"
)  # Code to create stacked barplot of booking status with respect to no. of previous bookings not cancelled

booking_status                            0      1    All
no_of_previous_bookings_not_canceled                     
All                                   24390  11885  36275
0                                     23585  11878  35463
1                                       224      4    228
12                                       11      1     12
4                                        64      1     65
6                                        35      1     36
2                                       112      0    112
44                                        2      0      2
43                                        1      0      1
42                                        1      0      1
41                                        1      0      1
40                                        1      0      1
38                                        1      0      1
39                                        1      0      1
46                                        1      0      1
37                                        1      0      1
36                                        1      0      1
35                                        1      0      1
45                                        1      0      1
48                                        2      0      2
47                                        1      0      1
33                                        1      0      1
49                                        1      0      1
50                                        1      0      1
51                                        1      0      1
52                                        1      0      1
53                                        1      0      1
54                                        1      0      1
55                                        1      0      1
56                                        1      0      1
57                                        1      0      1
58                                        1      0      1
34                                        1      0      1
31                                        2      0      2
32                                        2      0      2
3                                        80      0     80
5                                        60      0     60
7                                        24      0     24
8                                        23      0     23
9                                        19      0     19
10                                       19      0     19
11                                       15      0     15
13                                        7      0      7
14                                        9      0      9
15                                        8      0      8
16                                        7      0      7
17                                        6      0      6
18                                        6      0      6
19                                        6      0      6
20                                        6      0      6
21                                        6      0      6
22                                        6      0      6
23                                        3      0      3
24                                        3      0      3
25                                        3      0      3
26                                        2      0      2
27                                        3      0      3
28                                        2      0      2
29                                        2      0      2
30                                        2      0      2
------------------------------------------------------------------------------------------------------------------------

data[data["no_of_previous_bookings_not_canceled"] != 0][
    "booking_status"
].value_counts()

# Filter for non-canceled bookings
non_canceled_bookings = data[data['booking_status'] == 0]

# Count non-canceled bookings
num_non_canceled = non_canceled_bookings.shape[0]

# Calculate percentage
percentage_non_canceled = (num_non_canceled / data.shape[0]) * 100

# Print the result
print(f"Percentage of bookings not canceled: {percentage_non_canceled:.2f}%")

Percentage of bookings not canceled: 67.24%

stacked_barplot(
    data,"no_of_special_requests", "booking_status"
)  # Code to create stacked barplot of booking status with respect to no. of special requests

booking_status              0      1    All
no_of_special_requests                     
All                     24390  11885  36275
0                       11232   8545  19777
1                        8670   2703  11373
2                        3727    637   4364
3                         675      0    675
4                          78      0     78
5                           8      0      8
------------------------------------------------------------------------------------------------------------------------

# grouping the data on arrival months and extracting the count of bookings
monthly_data = data.groupby(["arrival_month"])["booking_status"].count()

# creating a dataframe with months and count of customers in each month
monthly_data = pd.DataFrame(
    {"Month": list(monthly_data.index), "Guests": list(monthly_data.values)}
)

# plotting the trend over different months
plt.figure(figsize=(10, 5))
sns.lineplot(data=monthly_data, x="Month", y="Guests")
plt.show()

def calculate_arrival_month_percentages(data):
  """
  Calculates the percentage of bookings for each arrival month.

  Args:
    data: The pandas DataFrame containing booking data.

  Returns:
    A pandas Series containing the percentage of bookings for each arrival month.
  """
  arrival_month_counts = data['arrival_month'].value_counts()
  total_bookings = data.shape[0]
  arrival_month_percentages = (arrival_month_counts / total_bookings) * 100
  return arrival_month_percentages

# Calculate and print the percentages
arrival_month_percentages = calculate_arrival_month_percentages(data)
print(arrival_month_percentages)

arrival_month
10   14.65748
9    12.71123
8    10.51137
6     8.82977
12    8.32805
11    8.21502
7     8.04962
4     7.54238
5     7.16196
3     6.50034
2     4.69745
1     2.79531
Name: count, dtype: float64

labeled_barplot(data,'market_segment_type')
def calculate_market_segment_percentages(data):
  """
  Calculates the percentage of bookings for each market segment type.

  Args:
    data: The pandas DataFrame containing booking data.

  Returns:
    A pandas Series containing the percentage of bookings for each market segment type.
  """
  market_segment_counts = data['market_segment_type'].value_counts()
  total_bookings = data.shape[0]
  market_segment_percentages = (market_segment_counts / total_bookings) * 100
  return market_segment_percentages

# Calculate and print the percentages
market_segment_percentages = calculate_market_segment_percentages(data)
print(market_segment_percentages)

market_segment_type
Online          63.99449
Offline         29.02274
Corporate        5.56030
Complementary    1.07788
Aviation         0.34459
Name: count, dtype: float64

plt.figure(figsize=(10, 6))
sns.boxplot(
    data=data, x="market_segment_type", y="avg_price_per_room"
)
plt.show()

# plot of data frame made of just the market_segment_type and avg_price_per_room

total = len(data["market_segment_type"])  # length of the column
count = data["market_segment_type"].nunique()  # counts amount of unique values for
plt.figure(figsize=(12, 7))  # sets figure size

plt.xticks(fontsize=15)  # rotates tick labels 90 degrees
#     create barplot
ax = sns.barplot(
    data=data[["market_segment_type", "avg_price_per_room"]],
    x="market_segment_type",
    y="avg_price_per_room",
    palette="deep",  # sets color for plot
    ci=None,
)
#     creates labels on top of bars that are either counts or perentages of the whole column depending perc value
for p in ax.patches:
    label = "€{:.2f}".format(p.get_height())  # count of each level of the category

    x = p.get_x() + p.get_width() / 2  # width of the plot
    y = p.get_height()  # height of the plot

    #         edits the labels to be the correct size and placement
    ax.annotate(
        label,
        (x, y),
        ha="center",
        va="center",
        size=15,
        xytext=(0, 5),
        textcoords="offset points",
    )  # annotate the percentage or the count

plt.savefig(
    "avg_room_price_per_market_segment.jpg", bbox_inches="tight"
)  # saves plot as JPEG
plt.show()  # show the plot

booking_status_counts = data['booking_status'].value_counts()

canceled_percentage = (booking_status_counts[1] / len(data)) * 100
print(f"Percentage of bookings canceled: {canceled_percentage:.2f}%")

Percentage of bookings canceled: 32.76%

data.groupby("booking_status")["repeated_guest"].value_counts()

# Filter for repeating guests
repeating_guests = data[data['repeated_guest'] == 1]

# Calculate cancellations within this group
repeating_guest_cancellations = repeating_guests[repeating_guests['booking_status'] == 1].shape[0]

# Calculate the percentage
percentage_repeating_guest_cancellations = (repeating_guest_cancellations / repeating_guests.shape[0]) * 100

# Print the result
print(f"Percentage of repeating guests who cancel: {percentage_repeating_guest_cancellations:.2f}%")

Percentage of repeating guests who cancel: 1.72%

stacked_barplot(
    data,"no_of_special_requests", "booking_status"
)  # Code to create stacked barplot of booking status with respect to no. of special requests

booking_status              0      1    All
no_of_special_requests                     
All                     24390  11885  36275
0                       11232   8545  19777
1                        8670   2703  11373
2                        3727    637   4364
3                         675      0    675
4                          78      0     78
5                           8      0      8
------------------------------------------------------------------------------------------------------------------------

data.isnull().sum() #Checking for missing values

# outlier detection using boxplot
numeric_columns = data.select_dtypes(include=np.number).columns.tolist()
# dropping booking_status
numeric_columns.remove("booking_status")

plt.figure(figsize=(15, 12))

for i, variable in enumerate(numeric_columns):
    plt.subplot(4, 4, i + 1)
    plt.boxplot(data[variable], whis=1.5)
    plt.tight_layout()
    plt.title(variable)

plt.show()

#Computing different functions to check performance
def model_performance_classification_statsmodels(model,predictors,target,threshold=0.5):
    #Checking which probabilities are greater than the threshold
    pred_temp = model.predict(predictors)>threshold
    #Rounding off the variables
    pred = np.round(pred_temp)

    #Metrics being used for model performance
    acc = accuracy_score(target,pred) #To compute the accuracy score
    recall = recall_score(target,pred) #To compute the recall score
    precision = precision_score(target,pred) #To compute the precision score
    f1 = f1_score(target,pred) #To compute the f1 score

    #Creating a dataframe for the metrics
    df_perf = pd.DataFrame({'Accuracy':acc,'Recall':recall,'Precision':precision,'F1':f1,},index=[0],)

    return df_perf

def model_performance_classification_statsmodels(model, predictors, target, threshold=0.5):
    # Convert predictors to a NumPy array with a suitable data type
    predictors = np.asarray(predictors, dtype=np.float64)
    #Checking which probabilities are greater than the threshold
    pred_temp = model.predict(predictors)>threshold
    #Rounding off the variables
    pred = np.round(pred_temp)
    #Calculating the performance metrics
    Accuracy = accuracy_score(target, pred)
    #print('Accuracy', Accuracy)
    Recall = recall_score(target, pred)
    #print('Recall', Recall)
    Precision = precision_score(target, pred)
    #print('Precision', Precision)
    F1_Score = f1_score(target, pred)
    #print('F1_Score', F1_Score)

    #Creating a dataframe to display the results
    df_perf = pd.DataFrame(
        {
            "Accuracy": [Accuracy],
            "Recall": [Recall],
            "Precision": [Precision],
            "F1_Score": [F1_Score],
        }
    )
    return df_perf

#Computing the confusion matrix
def confusion_matrix_statsmodels(model, predictors, target, threshold=0.5):
    """
    To plot the confusion_matrix with percentages

    model: classifier
    predictors: independent variables
    target: dependent variable
    threshold: threshold for classifying the observation as class 1
    """
    y_pred = model.predict(predictors) > threshold
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [
            ["{0:0.0f}".format(item) + "\n{0:.2%}".format(item / cm.flatten().sum())]
            for item in cm.flatten()
        ]
    ).reshape(2, 2)

    plt.figure(figsize=(6, 4))
    sns.heatmap(cm, annot=labels, fmt="")
    plt.ylabel("True label")
    plt.xlabel("Predicted label")

#Independent and dependent variables defined
x = data.drop(['booking_status'],axis=1)
y = data['booking_status']

#Adding constant
X = sm.add_constant(x)
X = pd.get_dummies(X,drop_first=True)

#Create a train and test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=1)

print('Shape of the training set:',X_train.shape)
print('Shape of test set:', X_test.shape)
print('Percentage of Classes in Training Set:',y_train.value_counts(normalize=True))
print('Percentage of Classes in Test Set:',y_test.value_counts(normalize=True))

Shape of the training set: (25392, 28)
Shape of test set: (10883, 28)
Percentage of Classes in Training Set: booking_status
0   0.67064
1   0.32936
Name: proportion, dtype: float64
Percentage of Classes in Test Set: booking_status
0   0.67638
1   0.32362
Name: proportion, dtype: float64

# creating dummy variables
X = pd.get_dummies(
    X,
    columns=X.select_dtypes(include=["object", "category"]).columns.tolist(),
    drop_first=True,
)  ## Complete the code to create dummies for independent features

X.head()

# Converting the input attributes into float type for modeling
X = X.astype(float)
X.head()

#Fitting the logistic regression model
logit = sm.Logit(y_train,X_train.astype(float))
lg = logit.fit(disp=False)
print(lg.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25364
Method:                           MLE   Df Model:                           27
Date:                Thu, 07 Nov 2024   Pseudo R-squ.:                  0.3292
Time:                        17:28:26   Log-Likelihood:                -10794.
converged:                      False   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                 -922.8266    120.832     -7.637      0.000   -1159.653    -686.000
no_of_adults                             0.1137      0.038      3.019      0.003       0.040       0.188
no_of_children                           0.1580      0.062      2.544      0.011       0.036       0.280
no_of_weekend_nights                     0.1067      0.020      5.395      0.000       0.068       0.145
no_of_week_nights                        0.0397      0.012      3.235      0.001       0.016       0.064
required_car_parking_space              -1.5943      0.138    -11.565      0.000      -1.865      -1.324
lead_time                                0.0157      0.000     58.863      0.000       0.015       0.016
arrival_year                             0.4561      0.060      7.617      0.000       0.339       0.573
arrival_month                           -0.0417      0.006     -6.441      0.000      -0.054      -0.029
arrival_date                             0.0005      0.002      0.259      0.796      -0.003       0.004
repeated_guest                          -2.3472      0.617     -3.806      0.000      -3.556      -1.139
no_of_previous_cancellations             0.2664      0.086      3.108      0.002       0.098       0.434
no_of_previous_bookings_not_canceled    -0.1727      0.153     -1.131      0.258      -0.472       0.127
avg_price_per_room                       0.0188      0.001     25.396      0.000       0.017       0.020
no_of_special_requests                  -1.4689      0.030    -48.782      0.000      -1.528      -1.410
type_of_meal_plan_Meal Plan 2            0.1756      0.067      2.636      0.008       0.045       0.306
type_of_meal_plan_Meal Plan 3           17.3584   3987.836      0.004      0.997   -7798.656    7833.373
type_of_meal_plan_Not Selected           0.2784      0.053      5.247      0.000       0.174       0.382
room_type_reserved_Room_Type 2          -0.3605      0.131     -2.748      0.006      -0.618      -0.103
room_type_reserved_Room_Type 3          -0.0012      1.310     -0.001      0.999      -2.568       2.566
room_type_reserved_Room_Type 4          -0.2823      0.053     -5.304      0.000      -0.387      -0.178
room_type_reserved_Room_Type 5          -0.7189      0.209     -3.438      0.001      -1.129      -0.309
room_type_reserved_Room_Type 6          -0.9501      0.151     -6.274      0.000      -1.247      -0.653
room_type_reserved_Room_Type 7          -1.4003      0.294     -4.770      0.000      -1.976      -0.825
market_segment_type_Complementary      -40.5975   5.65e+05  -7.19e-05      1.000   -1.11e+06    1.11e+06
market_segment_type_Corporate           -1.1924      0.266     -4.483      0.000      -1.714      -0.671
market_segment_type_Offline             -2.1946      0.255     -8.621      0.000      -2.694      -1.696
market_segment_type_Online              -0.3995      0.251     -1.590      0.112      -0.892       0.093
========================================================================================================

#Training Performance
print('Training Performance')
model_performance_classification_statsmodels(lg,X_train,y_train)

Training Performance

# Use Varianc Inflation Factor(VIF) to fix the multicollienarity issue
def checking_vif(predictors):
    # Select only numeric columns
    numeric_predictors = predictors.select_dtypes(include=['number'])

    # Drop rows with any NaN values in numeric columns
    numeric_predictors = numeric_predictors.dropna()

    vif = pd.DataFrame()
    vif['Features'] = numeric_predictors.columns

    # Calculating VIF for each feature
    vif['VIF'] = [variance_inflation_factor(numeric_predictors.values, i) for i in range(len(numeric_predictors.columns))]

    return vif

checking_vif(X_train)

# Convert all columns in X to numeric if possible.
# Errors='coerce' will replace non-numeric values with NaN.
for col in X.select_dtypes(include=['object']).columns:
    try:
        # Explicitly convert to numeric, handle errors by setting to NaN
        X[col] = pd.to_numeric(X[col], errors='coerce')
    except (ValueError, TypeError):
        # If conversion fails, drop the column and print a warning
        print(f"Column '{col}' cannot be converted to numeric and will be dropped.")
        X = X.drop(columns=[col])

# Impute NaN values using a strategy appropriate for numeric data
# Consider using mean, median, or a more sophisticated imputation method.
# Here, we use the mean for demonstration.
for col in X.select_dtypes(include=np.number).columns:
    X[col] = X[col].fillna(X[col].mean())

# Check if y is a pandas Series and convert it to a numpy array
if isinstance(y, pd.Series):
    y = y.to_numpy()

# *** The fix: Convert all columns in X to numeric dtype ***
X = X.astype(float)

#Initial list of columns
cols = X_train.columns.tolist()

#Setting an initial max p-value
max_p_value = 1

while len(cols) > 0:
    #Defining the train set
    x_train_aux = X_train[cols]

    # *** The fix: Ensure all columns in x_train_aux are numeric ***
    for col in x_train_aux.select_dtypes(include=['object']).columns:
        try:
            x_train_aux[col] = pd.to_numeric(x_train_aux[col], errors='coerce')
        except (ValueError, TypeError):
            print(f"Column '{col}' in x_train_aux cannot be converted to numeric and will be dropped.")
            x_train_aux = x_train_aux.drop(columns=[col])
            # If the column is dropped, also remove it from 'cols' to avoid further errors
            if col in cols:
                cols.remove(col)

    x_train_aux = x_train_aux.astype(float)


    #Fitting the model
    model = sm.Logit(y_train, x_train_aux).fit(disp=False)

    #Getting the p-values and the maximum p-value
    p_values = model.pvalues
    max_p_value = max(p_values)

    #Name of the variable with maximum p-value
    feature_with_p_max = p_values.idxmax()

    if max_p_value > 0.05:
        cols.remove(feature_with_p_max)
    else:
        break

selected_features = cols
print(selected_features)

['const', 'no_of_adults', 'no_of_children', 'no_of_weekend_nights', 'no_of_week_nights', 'required_car_parking_space', 'lead_time', 'arrival_year', 'arrival_month', 'repeated_guest', 'no_of_previous_cancellations', 'avg_price_per_room', 'no_of_special_requests', 'type_of_meal_plan_Meal Plan 2', 'type_of_meal_plan_Not Selected', 'room_type_reserved_Room_Type 2', 'room_type_reserved_Room_Type 4', 'room_type_reserved_Room_Type 5', 'room_type_reserved_Room_Type 6', 'room_type_reserved_Room_Type 7', 'market_segment_type_Corporate', 'market_segment_type_Offline']

X_train1 = X_train[selected_features]
X_test1 = X_test[selected_features]

logit1 = sm.Logit(y_train, X_train1.astype(float))
lg1 = logit1.fit(disp=False)
print(lg1.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                25392
Model:                          Logit   Df Residuals:                    25370
Method:                           MLE   Df Model:                           21
Date:                Thu, 07 Nov 2024   Pseudo R-squ.:                  0.3282
Time:                        17:28:29   Log-Likelihood:                -10810.
converged:                       True   LL-Null:                       -16091.
Covariance Type:            nonrobust   LLR p-value:                     0.000
==================================================================================================
                                     coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------
const                           -915.6391    120.471     -7.600      0.000   -1151.758    -679.520
no_of_adults                       0.1088      0.037      2.914      0.004       0.036       0.182
no_of_children                     0.1531      0.062      2.470      0.014       0.032       0.275
no_of_weekend_nights               0.1086      0.020      5.498      0.000       0.070       0.147
no_of_week_nights                  0.0417      0.012      3.399      0.001       0.018       0.066
required_car_parking_space        -1.5947      0.138    -11.564      0.000      -1.865      -1.324
lead_time                          0.0157      0.000     59.213      0.000       0.015       0.016
arrival_year                       0.4523      0.060      7.576      0.000       0.335       0.569
arrival_month                     -0.0425      0.006     -6.591      0.000      -0.055      -0.030
repeated_guest                    -2.7367      0.557     -4.916      0.000      -3.828      -1.646
no_of_previous_cancellations       0.2288      0.077      2.983      0.003       0.078       0.379
avg_price_per_room                 0.0192      0.001     26.336      0.000       0.018       0.021
no_of_special_requests            -1.4698      0.030    -48.884      0.000      -1.529      -1.411
type_of_meal_plan_Meal Plan 2      0.1642      0.067      2.469      0.014       0.034       0.295
type_of_meal_plan_Not Selected     0.2860      0.053      5.406      0.000       0.182       0.390
room_type_reserved_Room_Type 2    -0.3552      0.131     -2.709      0.007      -0.612      -0.098
room_type_reserved_Room_Type 4    -0.2828      0.053     -5.330      0.000      -0.387      -0.179
room_type_reserved_Room_Type 5    -0.7364      0.208     -3.535      0.000      -1.145      -0.328
room_type_reserved_Room_Type 6    -0.9682      0.151     -6.403      0.000      -1.265      -0.672
room_type_reserved_Room_Type 7    -1.4343      0.293     -4.892      0.000      -2.009      -0.860
market_segment_type_Corporate     -0.7913      0.103     -7.692      0.000      -0.993      -0.590
market_segment_type_Offline       -1.7854      0.052    -34.363      0.000      -1.887      -1.684
==================================================================================================

print('Training Performance')
model_performance_classification_statsmodels(lg1,X_train1,y_train)

Training Performance

#Converting coefficients to odds
odds = np.exp(lg1.params.astype(np.float64)) # Convert lg1.params to float64

#Finding the percentage change
perc_change_odds = (np.exp(lg1.params.astype(np.float64)) - 1) * 100 # Convert lg1.params to float64

#Removing limit from number of columns to display
pd.set_option("display.max_columns", None)

#Adding the odds to a dataframe
pd.DataFrame({"Odds": odds, "Change_odd%": perc_change_odds}, index=X_train1.columns).T

# creating confusion matrix
# Convert X_train1 columns to numeric type before prediction
X_train1_numeric = X_train1.astype(float) #Convert all columns to float64

confusion_matrix_statsmodels(lg1, X_train1_numeric, y_train)

log_model_train_perf = model_performance_classification_statsmodels(lg1,X_train1,y_train)

# Before prediction, ensure all columns are numeric and handle potential non-numeric values
X_train1 = X_train1.apply(pd.to_numeric, errors='coerce').fillna(0)

# Convert X_train1 columns to numeric type before prediction
X_train1_numeric = X_train1.astype(np.float64) # Use np.float64 for consistency

logit_roc_auc_train = roc_auc_score(y_train, lg1.predict(X_train1_numeric)) # Pass X_train1_numeric to predict
fpr, tpr, thresholds = roc_curve(y_train, lg1.predict(X_train1_numeric)) # Pass X_train1_numeric to predict
plt.figure(figsize=(7, 5))
plt.plot(fpr, tpr, label="Logistic Regression (area = %0.2f)" % logit_roc_auc_train)
plt.plot([0, 1], [0, 1], "r--")
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.01])
plt.xlabel("False Positive Rate")
plt.ylabel("True Positive Rate")
plt.title("Receiver operating characteristic")
plt.legend(loc="lower right")
plt.show()

# Before prediction, ensure all columns are numeric and handle potential non-numeric values
X_train1 = X_train1.apply(pd.to_numeric, errors='coerce').fillna(0)

# Convert X_train1 columns to numeric type before prediction
# Explicitly cast all columns to float64
X_train1 = X_train1.astype(np.float64)

# Optimal threshold as per AUC-ROC curve
# The optimal cut off would be where tpr is high and fpr is low
fpr, tpr, thresholds = roc_curve(y_train, lg1.predict(X_train1))

optimal_idx = np.argmax(tpr - fpr)
optimal_threshold_auc_roc = thresholds[optimal_idx]
print(optimal_threshold_auc_roc)

0.3700522558708252

confusion_matrix_statsmodels(lg1,X_train1,y_train,threshold=optimal_threshold_auc_roc)

# checking model performance for this model
log_reg_model_train_perf_threshold_auc_roc = model_performance_classification_statsmodels(
    lg1, X_train1, y_train, threshold=optimal_threshold_auc_roc
)
print("Training performance:")
log_reg_model_train_perf_threshold_auc_roc

Training performance:

y_scores = lg1.predict(X_train1)
prec, rec, tre = precision_recall_curve(y_train, y_scores,)


def plot_prec_recall_vs_tresh(precisions, recalls, thresholds):
    plt.plot(thresholds, precisions[:-1], "b--", label="precision")
    plt.plot(thresholds, recalls[:-1], "g--", label="recall")
    plt.xlabel("Threshold")
    plt.legend(loc="upper left")
    plt.ylim([0, 1])


plt.figure(figsize=(10, 7))
plot_prec_recall_vs_tresh(prec, rec, tre)
plt.show()

# setting the threshold
optimal_threshold_curve = 0.42

# setting the threshold
optimal_threshold_curve = 0.42

# Use optimal_threshold_curve as the threshold
confusion_matrix_statsmodels(lg1, X_train1, y_train, threshold=optimal_threshold_curve)

log_reg_model_train_perf_threshold_curve = model_performance_classification_statsmodels(
    lg1, X_train1, y_train, threshold=optimal_threshold_curve
)
print("Training performance:")
log_reg_model_train_perf_threshold_curve

Training performance:

# Assuming X_test1 is a pandas DataFrame or a NumPy array
X_test1 = X_test1.astype(np.float64)  # If it's a DataFrame
# or
X_test1 = X_test1.astype(float)  # If it's a NumPy array

# Now, call your confusion matrix function
confusion_matrix_statsmodels(lg1, X_test1, y_test)

#Metrics
log_reg_model_test_perf = model_performance_classification_statsmodels(lg1,X_test1,y_test) ## Complete the code to check performance on X_test1 and y_test

print("Test performance:")
log_reg_model_test_perf

Test performance:

logit_roc_auc_train = roc_auc_score(y_test, lg1.predict(X_test1))
fpr, tpr, thresholds = roc_curve(y_test, lg1.predict(X_test1))
plt.figure(figsize=(7, 5))
plt.plot(fpr, tpr, label="Logistic Regression (area = %0.2f)" % logit_roc_auc_train)
plt.plot([0, 1], [0, 1], "r--")
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.01])
plt.xlabel("False Positive Rate")
plt.ylabel("True Positive Rate")
plt.title("Receiver operating characteristic")
plt.legend(loc="lower right")
plt.show()

confusion_matrix_statsmodels(lg1,X_test1,y_test,threshold=optimal_threshold_auc_roc)

# checking model performance for this model
log_reg_model_test_perf_threshold_auc_roc = model_performance_classification_statsmodels(
    lg1, X_test1, y_test, threshold=optimal_threshold_auc_roc
)
print("Test performance:")
log_reg_model_test_perf_threshold_auc_roc

Test performance:

# Get predicted probabilities
y_pred_prob = lg1.predict(X_test1)

# Calculate precision and recall for different thresholds
precision, recall, thresholds = precision_recall_curve(y_test, y_pred_prob)

# Find the optimal threshold based on your criteria (e.g., F1-score)
# This is just an example, adapt it to your specific requirements
f1_scores = 2 * (precision * recall) / (precision + recall)
optimal_threshold_recall_precision = thresholds[np.argmax(f1_scores)]

# Now you can use the optimal threshold in your confusion matrix function call
confusion_matrix_statsmodels(lg1, X_test1, y_test, optimal_threshold_recall_precision)

#Metrics
log_reg_model_test_perf_threshold_curve = model_performance_classification_statsmodels(
    lg1, X_test1, y_test, threshold=optimal_threshold_recall_precision
)
print("Test performance:")
log_reg_model_test_perf_threshold_curve

Test performance:

# Assuming 'model_performance_classification_statsmodels' is a defined function
# and 'X_train1', 'y_train' are your training data
log_reg_model_train_perf = model_performance_classification_statsmodels(lg1, X_train1, y_train)

#Model Comparison Training Set
models_train_comp_df = pd.concat(
    [
        log_model_train_perf.T,
        log_reg_model_train_perf_threshold_auc_roc.T,
        log_reg_model_train_perf_threshold_curve.T,
    ],
    axis=1,
)
models_train_comp_df.columns = [
    "Logistic Regression-default Threshold",
    "Logistic Regression-0.37 Threshold",
    "Logistic Regression-0.42 Threshold",
]

print("Training performance comparison:")
models_train_comp_df

Training performance comparison:

#Model Comparison Test set
models_test_comp_df = pd.concat(
    [
        log_reg_model_test_perf.T,
        log_reg_model_test_perf_threshold_auc_roc.T,
        log_reg_model_test_perf_threshold_curve.T,
    ],
    axis=1,
)
models_test_comp_df.columns = [
    "Logistic Regression-default Threshold",
    "Logistic Regression-0.37 Threshold",
    "Logistic Regression-0.42 Threshold",
]

print("Test performance comparison:")
models_test_comp_df

Test performance comparison:

#Creating independent and dependent variables
X = data.drop(['booking_status'],axis=1)
Y = data['booking_status']

#Create dummy variables
X = pd.get_dummies(X, drop_first=True)

#Splitting for training and test data
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.30, random_state=1)

print("Shape of Training set : ", X_train.shape)
print("Shape of test set : ", X_test.shape)
print("Percentage of classes in training set:",y_train.value_counts(normalize=True))
print("Percentage of classes in test set:",y_test.value_counts(normalize=True))

Shape of Training set :  (25392, 27)
Shape of test set :  (10883, 27)
Percentage of classes in training set: booking_status
0   0.67064
1   0.32936
Name: proportion, dtype: float64
Percentage of classes in test set: booking_status
0   0.67638
1   0.32362
Name: proportion, dtype: float64

# defining a function to compute different metrics to check performance of a classification model built using sklearn
def model_performance_classification_sklearn(model, predictors, target):
    """
    Function to compute different metrics to check classification model performance

    model: classifier
    predictors: independent variables
    target: dependent variable
    """

    # predicting using the independent variables
    pred = model.predict(predictors)

    acc = accuracy_score(target, pred)  # to compute Accuracy
    recall = recall_score(target, pred)  # to compute Recall
    precision = precision_score(target, pred)  # to compute Precision
    f1 = f1_score(target, pred)  # to compute F1-score

    # creating a dataframe of metrics
    df_perf = pd.DataFrame(
        {"Accuracy": acc, "Recall": recall, "Precision": precision, "F1": f1,},
        index=[0],
    )

    return df_perf

def confusion_matrix_sklearn(model, predictors, target):
    """
    To plot the confusion_matrix with percentages

    model: classifier
    predictors: independent variables
    target: dependent variable
    """
    y_pred = model.predict(predictors)
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [
            ["{0:0.0f}".format(item) + "\n{0:.2%}".format(item / cm.flatten().sum())]
            for item in cm.flatten()
        ]
    ).reshape(2, 2)

    plt.figure(figsize=(6, 4))
    sns.heatmap(cm, annot=labels, fmt="")
    plt.ylabel("True label")
    plt.xlabel("Predicted label")

model = DecisionTreeClassifier(random_state=1)
model.fit(X_train,y_train)

DecisionTreeClassifier(random_state=1)

DecisionTreeClassifier(random_state=1)

confusion_matrix_sklearn(model,X_train,y_train)

decision_tree_perf_train_default = model_performance_classification_sklearn(
    model, X_train, y_train
)
decision_tree_perf_train_default

confusion_matrix_sklearn(model,X_test,y_test)

decision_tree_perf_test_default = model_performance_classification_sklearn(model,X_test,y_test) ## Complete the code to check performance on test set
decision_tree_perf_test_default

feature_names = list(X_train.columns)
importances = model.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(8, 8))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()

# Choose the type of classifier.
estimator = DecisionTreeClassifier(random_state=1, class_weight="balanced")

# Grid of parameters to choose from
parameters = {
    "max_depth": np.arange(2, 7, 2),
    "max_leaf_nodes": [50, 75, 150, 250],
    "min_samples_split": [10, 30, 50, 70],
}

# Type of scoring used to compare parameter combinations
acc_scorer = make_scorer(f1_score)

# Run the grid search
grid_obj = GridSearchCV(estimator, parameters, scoring=acc_scorer, cv=5)
grid_obj = grid_obj.fit(X_train, y_train)

# Set the clf to the best combination of parameters
estimator = grid_obj.best_estimator_

# Fit the best algorithm to the data.
estimator.fit(X_train, y_train)

DecisionTreeClassifier(class_weight='balanced', max_depth=6, max_leaf_nodes=50,
                       min_samples_split=10, random_state=1)

DecisionTreeClassifier(class_weight='balanced', max_depth=6, max_leaf_nodes=50,
                       min_samples_split=10, random_state=1)

confusion_matrix_sklearn(estimator,X_train,y_train)

decision_tree_tune_perf_train = model_performance_classification_sklearn(estimator,X_train,y_train)
decision_tree_tune_perf_train

decision_tree_tune_perf_test = model_performance_classification_sklearn(estimator,X_test,y_test)
decision_tree_tune_perf_test

plt.figure(figsize=(20, 10))
out = tree.plot_tree(
    estimator,
    feature_names=feature_names,
    filled=True,
    fontsize=9,
    node_ids=False,
    class_names=None,
)
# below code will add arrows to the decision tree split if they are missing
for o in out:
    arrow = o.arrow_patch
    if arrow is not None:
        arrow.set_edgecolor("black")
        arrow.set_linewidth(1)
plt.show()

# Text report showing the rules of a decision tree -
print(tree.export_text(estimator, feature_names=feature_names, show_weights=True))

|--- lead_time <= 151.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 196.50
|   |   |   |   |   |   |--- weights: [1736.39, 133.59] class: 0
|   |   |   |   |   |--- avg_price_per_room >  196.50
|   |   |   |   |   |   |--- weights: [0.75, 24.29] class: 1
|   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |--- weights: [960.27, 223.16] class: 0
|   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |--- weights: [129.73, 160.92] class: 1
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- lead_time <= 117.50
|   |   |   |   |   |--- avg_price_per_room <= 93.58
|   |   |   |   |   |   |--- weights: [214.72, 227.72] class: 1
|   |   |   |   |   |--- avg_price_per_room >  93.58
|   |   |   |   |   |   |--- weights: [82.76, 285.41] class: 1
|   |   |   |   |--- lead_time >  117.50
|   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |--- weights: [87.23, 81.98] class: 0
|   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |--- weights: [228.14, 48.58] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- lead_time <= 13.50
|   |   |   |   |--- avg_price_per_room <= 99.44
|   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |--- weights: [92.45, 0.00] class: 0
|   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |--- weights: [363.83, 132.08] class: 0
|   |   |   |   |--- avg_price_per_room >  99.44
|   |   |   |   |   |--- lead_time <= 3.50
|   |   |   |   |   |   |--- weights: [219.94, 85.01] class: 0
|   |   |   |   |   |--- lead_time >  3.50
|   |   |   |   |   |   |--- weights: [132.71, 280.85] class: 1
|   |   |   |--- lead_time >  13.50
|   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 71.92
|   |   |   |   |   |   |--- weights: [158.80, 159.40] class: 1
|   |   |   |   |   |--- avg_price_per_room >  71.92
|   |   |   |   |   |   |--- weights: [850.67, 3543.28] class: 1
|   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |--- weights: [48.46, 1.52] class: 0
|   |--- no_of_special_requests >  0.50
|   |   |--- no_of_special_requests <= 1.50
|   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |--- lead_time <= 102.50
|   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |--- weights: [697.09, 9.11] class: 0
|   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |--- weights: [15.66, 9.11] class: 0
|   |   |   |   |--- lead_time >  102.50
|   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |--- weights: [32.06, 19.74] class: 0
|   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |--- weights: [44.73, 3.04] class: 0
|   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |--- lead_time <= 8.50
|   |   |   |   |   |--- lead_time <= 4.50
|   |   |   |   |   |   |--- weights: [498.03, 44.03] class: 0
|   |   |   |   |   |--- lead_time >  4.50
|   |   |   |   |   |   |--- weights: [258.71, 63.76] class: 0
|   |   |   |   |--- lead_time >  8.50
|   |   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |   |--- weights: [2512.51, 1451.32] class: 0
|   |   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |   |--- weights: [134.20, 1.52] class: 0
|   |   |--- no_of_special_requests >  1.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |--- weights: [1585.04, 0.00] class: 0
|   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- weights: [180.42, 57.69] class: 0
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [52.19, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |--- weights: [184.90, 56.17] class: 0
|   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |--- weights: [106.61, 106.27] class: 0
|   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |--- weights: [67.10, 0.00] class: 0
|--- lead_time >  151.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- no_of_special_requests <= 0.50
|   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |--- lead_time <= 163.50
|   |   |   |   |   |   |--- weights: [3.73, 24.29] class: 1
|   |   |   |   |   |--- lead_time >  163.50
|   |   |   |   |   |   |--- weights: [257.96, 62.24] class: 0
|   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |--- avg_price_per_room <= 2.50
|   |   |   |   |   |   |--- weights: [8.95, 3.04] class: 0
|   |   |   |   |   |--- avg_price_per_room >  2.50
|   |   |   |   |   |   |--- weights: [0.75, 97.16] class: 1
|   |   |   |--- no_of_adults >  1.50
|   |   |   |   |--- avg_price_per_room <= 82.47
|   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |--- weights: [2.98, 282.37] class: 1
|   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |--- weights: [213.97, 385.60] class: 1
|   |   |   |   |--- avg_price_per_room >  82.47
|   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |--- weights: [23.86, 1030.80] class: 1
|   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |--- no_of_special_requests >  0.50
|   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |--- lead_time <= 180.50
|   |   |   |   |   |--- lead_time <= 159.50
|   |   |   |   |   |   |--- weights: [7.46, 7.59] class: 1
|   |   |   |   |   |--- lead_time >  159.50
|   |   |   |   |   |   |--- weights: [37.28, 4.55] class: 0
|   |   |   |   |--- lead_time >  180.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- weights: [20.13, 212.54] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [8.95, 0.00] class: 0
|   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |--- weights: [231.12, 110.82] class: 0
|   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |--- weights: [19.38, 34.92] class: 1
|   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |--- lead_time <= 348.50
|   |   |   |   |   |   |--- weights: [106.61, 3.04] class: 0
|   |   |   |   |   |--- lead_time >  348.50
|   |   |   |   |   |   |--- weights: [5.96, 4.55] class: 0
|   |--- avg_price_per_room >  100.04
|   |   |--- arrival_month <= 11.50
|   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |--- weights: [0.00, 3200.19] class: 1
|   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |--- weights: [23.11, 0.00] class: 0
|   |   |--- arrival_month >  11.50
|   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |--- weights: [35.04, 0.00] class: 0
|   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |--- weights: [3.73, 22.77] class: 1

# importance of features in the tree building

importances = estimator.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(8, 8))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()

clf = DecisionTreeClassifier(random_state=1, class_weight="balanced")
path = clf.cost_complexity_pruning_path(X_train, y_train)
ccp_alphas, impurities = abs(path.ccp_alphas), path.impurities

pd.DataFrame(path)

fig, ax = plt.subplots(figsize=(10, 5))
ax.plot(ccp_alphas[:-1], impurities[:-1], marker="o", drawstyle="steps-post")
ax.set_xlabel("effective alpha")
ax.set_ylabel("total impurity of leaves")
ax.set_title("Total Impurity vs effective alpha for training set")
plt.show()

clfs = []
for ccp_alpha in ccp_alphas:
    clf = DecisionTreeClassifier(
        random_state=1, ccp_alpha=ccp_alpha, class_weight="balanced"
    )
    clf.fit(X_train, y_train) ## Complete the code to fit decision tree on training data
    clfs.append(clf)
print(
    "Number of nodes in the last tree is: {} with ccp_alpha: {}".format(
        clfs[-1].tree_.node_count, ccp_alphas[-1]
    )
)

Number of nodes in the last tree is: 1 with ccp_alpha: 0.0811791438913696

clfs = clfs[:-1]
ccp_alphas = ccp_alphas[:-1]

node_counts = [clf.tree_.node_count for clf in clfs]
depth = [clf.tree_.max_depth for clf in clfs]
fig, ax = plt.subplots(2, 1, figsize=(10, 7))
ax[0].plot(ccp_alphas, node_counts, marker="o", drawstyle="steps-post")
ax[0].set_xlabel("alpha")
ax[0].set_ylabel("number of nodes")
ax[0].set_title("Number of nodes vs alpha")
ax[1].plot(ccp_alphas, depth, marker="o", drawstyle="steps-post")
ax[1].set_xlabel("alpha")
ax[1].set_ylabel("depth of tree")
ax[1].set_title("Depth vs alpha")
fig.tight_layout()

f1_train = []
for clf in clfs:
    pred_train = clf.predict(X_train)
    values_train = f1_score(y_train, pred_train)
    f1_train.append(values_train)

f1_test = []
for clf in clfs:
    pred_test = clf.predict(X_test)
    values_test = f1_score(y_test, pred_test)
    f1_test.append(values_test)

fig, ax = plt.subplots(figsize=(15, 5))
ax.set_xlabel("alpha")
ax.set_ylabel("F1 Score")
ax.set_title("F1 Score vs alpha for training and testing sets")
ax.plot(ccp_alphas, f1_train, marker="o", label="train", drawstyle="steps-post")
ax.plot(ccp_alphas, f1_test, marker="o", label="test", drawstyle="steps-post")
ax.legend()
plt.show()

index_best_model = np.argmax(f1_test)
best_model = clfs[index_best_model]
print(best_model)

DecisionTreeClassifier(ccp_alpha=0.00012267633155167043,
                       class_weight='balanced', random_state=1)

confusion_matrix_sklearn(best_model, X_train, y_train)

decision_tree_post_perf_train = model_performance_classification_sklearn(
    best_model, X_train, y_train
)
decision_tree_post_perf_train

#Confusion Matrix
confusion_matrix_sklearn(best_model, X_test, y_test)

#Metrics
decision_tree_test =  model_performance_classification_sklearn(best_model,X_train,y_train)
decision_tree_test

plt.figure(figsize=(20, 10))

out = tree.plot_tree(
    best_model,
    feature_names=feature_names,
    filled=True,
    fontsize=9,
    node_ids=False,
    class_names=None,
)
for o in out:
    arrow = o.arrow_patch
    if arrow is not None:
        arrow.set_edgecolor("black")
        arrow.set_linewidth(1)
plt.show()

# Text report showing the rules of a decision tree -

print(tree.export_text(best_model, feature_names=feature_names, show_weights=True))

|--- lead_time <= 151.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 196.50
|   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |--- lead_time <= 16.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 68.50
|   |   |   |   |   |   |   |   |   |--- weights: [207.26, 10.63] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  68.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 29.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |--- arrival_date >  29.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 7.59] class: 1
|   |   |   |   |   |   |   |--- lead_time >  16.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 135.00
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_previous_bookings_not_canceled <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- no_of_previous_bookings_not_canceled >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [21.62, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  135.00
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 12.14] class: 1
|   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |--- weights: [1199.59, 1.52] class: 0
|   |   |   |   |   |--- avg_price_per_room >  196.50
|   |   |   |   |   |   |--- weights: [0.75, 24.29] class: 1
|   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 63.29
|   |   |   |   |   |   |   |   |--- arrival_date <= 20.50
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [41.75, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 3.04] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  20.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 59.75
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 23.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.49, 12.14] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  23.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [14.91, 1.52] class: 0
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  59.75
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 44.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 59.21] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  44.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  63.29
|   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 3.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 59.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- lead_time >  59.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [20.13, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  3.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.75, 15.18] class: 1
|   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |--- weights: [413.04, 27.33] class: 0
|   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |--- avg_price_per_room <= 99.98
|   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 62.50
|   |   |   |   |   |   |   |   |   |--- weights: [15.66, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  62.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 80.38
|   |   |   |   |   |   |   |   |   |   |--- weights: [8.20, 25.81] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  80.38
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |   |--- weights: [55.17, 3.04] class: 0
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 73.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |   |--- lead_time >  73.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [21.62, 4.55] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  99.98
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- weights: [8.95, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 132.43
|   |   |   |   |   |   |   |   |   |--- weights: [9.69, 122.97] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  132.43
|   |   |   |   |   |   |   |   |   |--- weights: [6.71, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- lead_time <= 117.50
|   |   |   |   |   |--- avg_price_per_room <= 93.58
|   |   |   |   |   |   |--- avg_price_per_room <= 75.07
|   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 58.75
|   |   |   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  58.75
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 118.41] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 11.50
|   |   |   |   |   |   |   |   |   |--- weights: [31.31, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  11.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 6.07] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [5.96, 9.11] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  75.07
|   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |--- weights: [59.64, 3.04] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.49, 16.70] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 86.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 16.70] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  86.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [8.95, 3.04] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 22.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [44.73, 4.55] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  22.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |--- avg_price_per_room >  93.58
|   |   |   |   |   |   |--- arrival_date <= 11.50
|   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |--- weights: [16.40, 39.47] class: 1
|   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |--- weights: [20.13, 6.07] class: 0
|   |   |   |   |   |   |--- arrival_date >  11.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 102.09
|   |   |   |   |   |   |   |   |--- weights: [5.22, 144.22] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  102.09
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 109.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 16.70] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [33.55, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  109.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 124.25
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.98, 75.91] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  124.25
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 3.04] class: 0
|   |   |   |   |--- lead_time >  117.50
|   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |--- arrival_date <= 7.50
|   |   |   |   |   |   |   |--- weights: [38.02, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_date >  7.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 93.58
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 65.38
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  65.38
|   |   |   |   |   |   |   |   |   |--- weights: [24.60, 3.04] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  93.58
|   |   |   |   |   |   |   |   |--- arrival_date <= 28.00
|   |   |   |   |   |   |   |   |   |--- weights: [14.91, 72.87] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  28.00
|   |   |   |   |   |   |   |   |   |--- weights: [9.69, 1.52] class: 0
|   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |--- weights: [84.25, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |--- lead_time <= 125.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 90.85
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 87.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [13.42, 13.66] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  87.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 15.18] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  90.85
|   |   |   |   |   |   |   |   |   |--- weights: [10.44, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  125.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 19.50
|   |   |   |   |   |   |   |   |   |--- weights: [58.15, 18.22] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  19.50
|   |   |   |   |   |   |   |   |   |--- weights: [61.88, 1.52] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- lead_time <= 13.50
|   |   |   |   |--- avg_price_per_room <= 99.44
|   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |--- weights: [92.45, 0.00] class: 0
|   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 70.05
|   |   |   |   |   |   |   |   |   |--- weights: [31.31, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  70.05
|   |   |   |   |   |   |   |   |   |--- lead_time <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [38.77, 1.52] class: 0
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |--- lead_time >  5.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [6.71, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [34.30, 40.99] class: 1
|   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 19.74] class: 1
|   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 2.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 74.21
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 3.04] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  74.21
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [9.69, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  2.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 10.63] class: 1
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |   |   |   |--- weights: [155.07, 6.07] class: 0
|   |   |   |   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- weights: [3.73, 10.63] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [7.46, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  99.44
|   |   |   |   |   |--- lead_time <= 3.50
|   |   |   |   |   |   |--- avg_price_per_room <= 202.67
|   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |--- weights: [63.37, 30.36] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 20.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [115.56, 12.14] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  20.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [28.33, 3.04] class: 0
|   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 6.07] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  202.67
|   |   |   |   |   |   |   |--- weights: [0.75, 22.77] class: 1
|   |   |   |   |   |--- lead_time >  3.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 119.25
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 118.50
|   |   |   |   |   |   |   |   |   |--- weights: [18.64, 59.21] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  118.50
|   |   |   |   |   |   |   |   |   |--- weights: [8.20, 1.52] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  119.25
|   |   |   |   |   |   |   |   |--- weights: [34.30, 171.55] class: 1
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- weights: [26.09, 1.52] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 14.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [9.69, 36.43] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  14.00
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 208.67
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  208.67
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [15.66, 0.00] class: 0
|   |   |   |--- lead_time >  13.50
|   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |--- avg_price_per_room <= 71.92
|   |   |   |   |   |   |--- avg_price_per_room <= 59.43
|   |   |   |   |   |   |   |--- lead_time <= 84.50
|   |   |   |   |   |   |   |   |--- weights: [50.70, 7.59] class: 0
|   |   |   |   |   |   |   |--- lead_time >  84.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 27.00
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 131.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 15.18] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  131.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  27.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- weights: [10.44, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  59.43
|   |   |   |   |   |   |   |--- lead_time <= 25.50
|   |   |   |   |   |   |   |   |--- weights: [20.88, 6.07] class: 0
|   |   |   |   |   |   |   |--- lead_time >  25.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.34
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [15.66, 78.94] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 102.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  102.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [12.67, 3.04] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.34
|   |   |   |   |   |   |   |   |   |--- weights: [11.18, 0.00] class: 0
|   |   |   |   |   |--- avg_price_per_room >  71.92
|   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |--- lead_time <= 65.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 120.45
|   |   |   |   |   |   |   |   |   |--- weights: [79.77, 9.11] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  120.45
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 12.14] class: 1
|   |   |   |   |   |   |   |--- lead_time >  65.50
|   |   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 <= 0.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 27.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [16.40, 47.06] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  27.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 >  0.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 63.76] class: 1
|   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 104.31
|   |   |   |   |   |   |   |   |--- lead_time <= 25.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [16.40, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [38.77, 118.41] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  25.50
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [39.51, 185.21] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [73.81, 411.41] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  104.31
|   |   |   |   |   |   |   |   |--- arrival_month <= 10.50
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 5 <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 195.30
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 9
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  195.30
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 138.15] class: 1
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 5 >  0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 22.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 6.07] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  22.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 9.11] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  10.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 168.06
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 22.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  22.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [17.15, 83.50] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  168.06
|   |   |   |   |   |   |   |   |   |   |--- weights: [12.67, 6.07] class: 0
|   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |--- weights: [48.46, 1.52] class: 0
|   |--- no_of_special_requests >  0.50
|   |   |--- no_of_special_requests <= 1.50
|   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |--- lead_time <= 102.50
|   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |--- weights: [697.09, 9.11] class: 0
|   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |--- lead_time <= 63.00
|   |   |   |   |   |   |   |--- weights: [15.66, 1.52] class: 0
|   |   |   |   |   |   |--- lead_time >  63.00
|   |   |   |   |   |   |   |--- weights: [0.00, 7.59] class: 1
|   |   |   |   |--- lead_time >  102.50
|   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |--- lead_time <= 105.00
|   |   |   |   |   |   |   |--- weights: [0.75, 6.07] class: 1
|   |   |   |   |   |   |--- lead_time >  105.00
|   |   |   |   |   |   |   |--- weights: [31.31, 13.66] class: 0
|   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |--- weights: [44.73, 3.04] class: 0
|   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |--- lead_time <= 8.50
|   |   |   |   |   |--- lead_time <= 4.50
|   |   |   |   |   |   |--- no_of_week_nights <= 10.00
|   |   |   |   |   |   |   |--- weights: [498.03, 40.99] class: 0
|   |   |   |   |   |   |--- no_of_week_nights >  10.00
|   |   |   |   |   |   |   |--- weights: [0.00, 3.04] class: 1
|   |   |   |   |   |--- lead_time >  4.50
|   |   |   |   |   |   |--- arrival_date <= 13.50
|   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |--- weights: [58.90, 36.43] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |--- weights: [33.55, 1.52] class: 0
|   |   |   |   |   |   |--- arrival_date >  13.50
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |--- weights: [123.76, 9.11] class: 0
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 126.33
|   |   |   |   |   |   |   |   |   |--- weights: [32.80, 3.04] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  126.33
|   |   |   |   |   |   |   |   |   |--- weights: [9.69, 13.66] class: 1
|   |   |   |   |--- lead_time >  8.50
|   |   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |   |--- avg_price_per_room <= 118.55
|   |   |   |   |   |   |   |--- lead_time <= 61.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [70.08, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [126.74, 1.52] class: 0
|   |   |   |   |   |   |   |--- lead_time >  61.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 57.69] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 66.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  66.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.93
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [54.43, 3.04] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.93
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 10
|   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |--- avg_price_per_room >  118.55
|   |   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 19.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 177.15
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  177.15
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 6.07] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  19.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 27.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 121.20
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [18.64, 6.07] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  121.20
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |--- arrival_date >  27.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 55.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  55.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [11.93, 10.63] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [37.28, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 119.20
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [9.69, 28.84] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  119.20
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 12
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 100.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [49.95, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  100.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.75, 18.22] class: 1
|   |   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |   |--- weights: [134.20, 1.52] class: 0
|   |   |--- no_of_special_requests >  1.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |--- weights: [1585.04, 0.00] class: 0
|   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- no_of_week_nights <= 9.50
|   |   |   |   |   |   |   |--- lead_time <= 6.50
|   |   |   |   |   |   |   |   |--- weights: [32.06, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  6.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 1.52] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  5.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 93.09
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  93.09
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [77.54, 27.33] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [19.38, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_week_nights >  9.50
|   |   |   |   |   |   |   |--- weights: [0.00, 3.04] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [52.19, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |--- avg_price_per_room <= 202.95
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.49, 9.11] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |--- weights: [8.20, 3.04] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- lead_time <= 150.50
|   |   |   |   |   |   |   |   |   |--- weights: [175.20, 28.84] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  150.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  202.95
|   |   |   |   |   |   |   |--- weights: [0.00, 10.63] class: 1
|   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |--- avg_price_per_room <= 153.15
|   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 2 <= 0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.12
|   |   |   |   |   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.12
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 90.42
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [12.67, 7.59] class: 0
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  90.42
|   |   |   |   |   |   |   |   |   |   |--- weights: [64.12, 60.72] class: 0
|   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 2 >  0.50
|   |   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  153.15
|   |   |   |   |   |   |   |--- weights: [12.67, 3.04] class: 0
|   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |--- weights: [67.10, 0.00] class: 0
|--- lead_time >  151.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- no_of_special_requests <= 0.50
|   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |--- lead_time <= 163.50
|   |   |   |   |   |   |--- arrival_month <= 5.00
|   |   |   |   |   |   |   |--- weights: [2.98, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  5.00
|   |   |   |   |   |   |   |--- weights: [0.75, 24.29] class: 1
|   |   |   |   |   |--- lead_time >  163.50
|   |   |   |   |   |   |--- lead_time <= 341.00
|   |   |   |   |   |   |   |--- lead_time <= 173.00
|   |   |   |   |   |   |   |   |--- arrival_date <= 3.50
|   |   |   |   |   |   |   |   |   |--- weights: [46.97, 9.11] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  3.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 13.66] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  173.00
|   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [6.71, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |--- weights: [188.62, 7.59] class: 0
|   |   |   |   |   |   |--- lead_time >  341.00
|   |   |   |   |   |   |   |--- weights: [13.42, 27.33] class: 1
|   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |--- avg_price_per_room <= 2.50
|   |   |   |   |   |   |--- lead_time <= 285.50
|   |   |   |   |   |   |   |--- weights: [8.20, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  285.50
|   |   |   |   |   |   |   |--- weights: [0.75, 3.04] class: 1
|   |   |   |   |   |--- avg_price_per_room >  2.50
|   |   |   |   |   |   |--- weights: [0.75, 97.16] class: 1
|   |   |   |--- no_of_adults >  1.50
|   |   |   |   |--- avg_price_per_room <= 82.47
|   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |--- weights: [2.98, 282.37] class: 1
|   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |--- lead_time <= 244.00
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 166.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  166.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 57.69] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [17.89, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 3.04] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 12.14] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [75.30, 12.14] class: 0
|   |   |   |   |   |   |   |--- lead_time >  244.00
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- weights: [25.35, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 80.38
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.18, 264.15] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  80.38
|   |   |   |   |   |   |   |   |   |   |--- weights: [7.46, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |--- weights: [46.22, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  82.47
|   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |--- lead_time <= 324.50
|   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |--- weights: [7.46, 986.78] class: 1
|   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 10.63] class: 1
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.47, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 19.74] class: 1
|   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  324.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 89.00
|   |   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  89.00
|   |   |   |   |   |   |   |   |--- weights: [0.75, 13.66] class: 1
|   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |--- weights: [5.22, 0.00] class: 0
|   |   |--- no_of_special_requests >  0.50
|   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |--- lead_time <= 180.50
|   |   |   |   |   |--- lead_time <= 159.50
|   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |--- weights: [5.96, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |--- weights: [1.49, 7.59] class: 1
|   |   |   |   |   |--- lead_time >  159.50
|   |   |   |   |   |   |--- arrival_date <= 1.50
|   |   |   |   |   |   |   |--- weights: [1.49, 3.04] class: 1
|   |   |   |   |   |   |--- arrival_date >  1.50
|   |   |   |   |   |   |   |--- weights: [35.79, 1.52] class: 0
|   |   |   |   |--- lead_time >  180.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |   |   |--- weights: [12.67, 3.04] class: 0
|   |   |   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 3.04] class: 1
|   |   |   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |   |   |--- weights: [7.46, 206.46] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [8.95, 0.00] class: 0
|   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |--- avg_price_per_room <= 76.48
|   |   |   |   |   |   |   |--- weights: [46.97, 4.55] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  76.48
|   |   |   |   |   |   |   |--- no_of_week_nights <= 6.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 27.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 233.00
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 152.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.49, 4.55] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  152.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- lead_time >  233.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [23.11, 19.74] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  27.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.24, 15.18] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 269.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  269.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.55] class: 1
|   |   |   |   |   |   |   |--- no_of_week_nights >  6.50
|   |   |   |   |   |   |   |   |--- weights: [4.47, 13.66] class: 1
|   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |--- arrival_date <= 14.50
|   |   |   |   |   |   |   |--- weights: [8.20, 3.04] class: 0
|   |   |   |   |   |   |--- arrival_date >  14.50
|   |   |   |   |   |   |   |--- weights: [11.18, 31.88] class: 1
|   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |--- lead_time <= 348.50
|   |   |   |   |   |   |--- weights: [106.61, 3.04] class: 0
|   |   |   |   |   |--- lead_time >  348.50
|   |   |   |   |   |   |--- weights: [5.96, 4.55] class: 0
|   |--- avg_price_per_room >  100.04
|   |   |--- arrival_month <= 11.50
|   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |--- weights: [0.00, 3200.19] class: 1
|   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |--- weights: [23.11, 0.00] class: 0
|   |   |--- arrival_month >  11.50
|   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |--- weights: [35.04, 0.00] class: 0
|   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |--- weights: [3.73, 0.00] class: 0
|   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |--- weights: [3.73, 22.77] class: 1

importances = best_model.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(12, 12))
plt.title("Feature Importances")
plt.barh(range(len(indices)), importances[indices], color="violet", align="center")
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel("Relative Importance")
plt.show()

#Training performance comparison
models_train_comp_df = pd.concat(
    [
      decision_tree_perf_train_default.T,
       decision_tree_tune_perf_train.T,
        decision_tree_post_perf_train.T,
    ],
    axis=1,
)
models_train_comp_df.columns = [
    "Decision Tree sklearn",
    "Decision Tree (Pre-Pruning)",
    "Decision Tree (Post-Pruning)",
]
print("Training performance comparison:")
models_train_comp_df

Training performance comparison:

#Testing performance comparison
models_test_comp_df = pd.concat(
[
    decision_tree_perf_test_default.T,
    decision_tree_tune_perf_test.T,
    decision_tree_test.T,

],
axis=1,)

models_test_comp_df.columns = [
    "Decision Tree sklearn",
    "Decision Tree (Pre-Pruning)",
    "Decision Tree (Post-Pruning)",
]
print("Testing performance comparison:")
models_test_comp_df

Testing performance comparison:

	count	mean	std	min	25%	50%	75%	max
no_of_adults	36275.00000	1.84496	0.51871	0.00000	2.00000	2.00000	2.00000	4.00000
no_of_children	36275.00000	0.10528	0.40265	0.00000	0.00000	0.00000	0.00000	10.00000
no_of_weekend_nights	36275.00000	0.81072	0.87064	0.00000	0.00000	1.00000	2.00000	7.00000
no_of_week_nights	36275.00000	2.20430	1.41090	0.00000	1.00000	2.00000	3.00000	17.00000
required_car_parking_space	36275.00000	0.03099	0.17328	0.00000	0.00000	0.00000	0.00000	1.00000
lead_time	36275.00000	85.23256	85.93082	0.00000	17.00000	57.00000	126.00000	443.00000
arrival_year	36275.00000	2017.82043	0.38384	2017.00000	2018.00000	2018.00000	2018.00000	2018.00000
arrival_month	36275.00000	7.42365	3.06989	1.00000	5.00000	8.00000	10.00000	12.00000
arrival_date	36275.00000	15.59700	8.74045	1.00000	8.00000	16.00000	23.00000	31.00000
repeated_guest	36275.00000	0.02564	0.15805	0.00000	0.00000	0.00000	0.00000	1.00000
no_of_previous_cancellations	36275.00000	0.02335	0.36833	0.00000	0.00000	0.00000	0.00000	13.00000
no_of_previous_bookings_not_canceled	36275.00000	0.15341	1.75417	0.00000	0.00000	0.00000	0.00000	58.00000
avg_price_per_room	36275.00000	103.42354	35.08942	0.00000	80.30000	99.45000	120.00000	540.00000
no_of_special_requests	36275.00000	0.61966	0.78624	0.00000	0.00000	0.00000	1.00000	5.00000

	const	no_of_adults	no_of_weekend_nights	no_of_week_nights	lead_time	arrival_year	arrival_month	arrival_date	avg_price_per_room	no_of_special_requests	type_of_meal_plan_Not Selected	market_segment_type_Offline	market_segment_type_Online
0	1.00000	2.00000	1.00000	2.00000	224.00000	2017.00000	10.00000	2.00000	65.00000	0.00000	0.00000	1.00000	0.00000
1	1.00000	2.00000	2.00000	3.00000	5.00000	2018.00000	11.00000	6.00000	106.68000	1.00000	1.00000	0.00000	1.00000
2	1.00000	1.00000	2.00000	1.00000	1.00000	2018.00000	2.00000	28.00000	60.00000	0.00000	0.00000	0.00000	1.00000
3	1.00000	2.00000	0.00000	2.00000	211.00000	2018.00000	5.00000	20.00000	100.00000	0.00000	0.00000	0.00000	1.00000
4	1.00000	2.00000	1.00000	1.00000	48.00000	2018.00000	4.00000	11.00000	94.50000	0.00000	1.00000	0.00000	1.00000

	const	no_of_adults	no_of_children	no_of_weekend_nights	no_of_week_nights	required_car_parking_space	lead_time	arrival_year	arrival_month	repeated_guest	no_of_previous_cancellations	avg_price_per_room	no_of_special_requests	type_of_meal_plan_Meal Plan 2	type_of_meal_plan_Not Selected	room_type_reserved_Room_Type 2	room_type_reserved_Room_Type 4	room_type_reserved_Room_Type 5	room_type_reserved_Room_Type 6	room_type_reserved_Room_Type 7	market_segment_type_Corporate	market_segment_type_Offline
Odds	0.00000	1.11491	1.16546	1.11470	1.04258	0.20296	1.01583	1.57195	0.95839	0.06478	1.25712	1.01937	0.22996	1.17846	1.33109	0.70104	0.75364	0.47885	0.37977	0.23827	0.45326	0.16773
Change_odd%	-100.00000	11.49096	16.54593	11.46966	4.25841	-79.70395	1.58331	57.19508	-4.16120	-93.52180	25.71181	1.93684	-77.00374	17.84641	33.10947	-29.89588	-24.63551	-52.11548	-62.02290	-76.17294	-54.67373	-83.22724

	Logistic Regression-default Threshold	Logistic Regression-0.37 Threshold	Logistic Regression-0.42 Threshold
Accuracy	0.80545	0.79265	0.80132
Recall	0.63267	0.73622	0.69939
Precision	0.73907	0.66808	0.69797
F1_Score	0.68174	0.70049	0.69868

	Logistic Regression-default Threshold	Logistic Regression-0.37 Threshold	Logistic Regression-0.42 Threshold
Accuracy	0.80465	0.79555	0.79224
Recall	0.63089	0.73964	0.75923
Precision	0.72900	0.66573	0.65427
F1_Score	0.67641	0.70074	0.70285

	Booking_ID	no_of_adults	no_of_weekend_nights	no_of_week_nights	type_of_meal_plan	room_type_reserved	lead_time	arrival_year	arrival_month	arrival_date	market_segment_type	avg_price_per_room	no_of_special_requests	booking_status
0	INN00001	2	1	2	Meal Plan 1	Room_Type 1	224	2017	10	2	Offline	65.00000	0	Not_Canceled
1	INN00002	2	2	3	Not Selected	Room_Type 1	5	2018	11	6	Online	106.68000	1	Not_Canceled
2	INN00003	1	2	1	Meal Plan 1	Room_Type 1	1	2018	2	28	Online	60.00000	0	Canceled
3	INN00004	2	0	2	Meal Plan 1	Room_Type 1	211	2018	5	20	Online	100.00000	0	Canceled
4	INN00005	2	1	1	Not Selected	Room_Type 1	48	2018	4	11	Online	94.50000	0	Canceled

	Booking_ID	no_of_adults	no_of_weekend_nights	no_of_week_nights	type_of_meal_plan	room_type_reserved	lead_time	arrival_year	arrival_month	arrival_date	market_segment_type	avg_price_per_room	no_of_special_requests	booking_status
36270	INN36271	3	2	6	Meal Plan 1	Room_Type 4	85	2018	8	3	Online	167.80000	1	Not_Canceled
36271	INN36272	2	1	3	Meal Plan 1	Room_Type 1	228	2018	10	17	Online	90.95000	2	Canceled
36272	INN36273	2	2	6	Meal Plan 1	Room_Type 1	148	2018	7	1	Online	98.39000	2	Not_Canceled
36273	INN36274	2	0	3	Not Selected	Room_Type 1	63	2018	4	21	Online	94.50000	0	Canceled
36274	INN36275	2	1	2	Meal Plan 1	Room_Type 1	207	2018	12	30	Offline	161.67000	0	Not_Canceled

	0
Booking_ID	0
no_of_adults	0
no_of_children	0
no_of_weekend_nights	0
no_of_week_nights	0
type_of_meal_plan	0
required_car_parking_space	0
room_type_reserved	0
lead_time	0
arrival_year	0
arrival_month	0
arrival_date	0
market_segment_type	0
repeated_guest	0
no_of_previous_cancellations	0
no_of_previous_bookings_not_canceled	0
avg_price_per_room	0
no_of_special_requests	0
booking_status	0

	Features	VIF
0	const	34866123.37597
1	no_of_adults	1.21461
2	no_of_children	1.17572
3	no_of_weekend_nights	1.05287
4	no_of_week_nights	1.06931
5	required_car_parking_space	1.03415
6	lead_time	1.15845
7	arrival_year	1.26424
8	arrival_month	1.24097
9	arrival_date	1.00486
10	repeated_guest	1.56324
11	no_of_previous_cancellations	1.37579
12	no_of_previous_bookings_not_canceled	1.63420
13	avg_price_per_room	1.39658
14	no_of_special_requests	1.11675

	ccp_alphas	impurities
0	0.00000	0.00838
1	0.00000	0.00838
2	0.00000	0.00838
3	0.00000	0.00838
4	0.00000	0.00838
...	...	...
1839	0.00890	0.32806
1840	0.00980	0.33786
1841	0.01272	0.35058
1842	0.03412	0.41882
1843	0.08118	0.50000

	Decision Tree sklearn	Decision Tree (Pre-Pruning)	Decision Tree (Post-Pruning)
Accuracy	0.99421	0.83097	0.89954
Recall	0.98661	0.78608	0.90303
Precision	0.99578	0.72425	0.81274
F1	0.99117	0.75390	0.85551

	Decision Tree sklearn	Decision Tree (Pre-Pruning)	Decision Tree (Post-Pruning)
Accuracy	0.87118	0.83497	0.89954
Recall	0.81175	0.78336	0.90303
Precision	0.79461	0.72758	0.81274
F1	0.80309	0.75444	0.85551

INN Hotels Project¶

Context¶

Objective¶

Data Description¶

Problem Definition¶

Importing necessary libraries and data¶

Import Dataset¶

Data Overview¶

Exploratory Data Analysis (EDA)¶

Univariate Analysis¶

Observations on No_of_Adults¶

Observations on number of children¶

Observations on number of weekend nights¶

Observations on number of week nights¶

Observations on type of meal plan¶

Observations on required car parking space¶

Observations on room type reserved¶

Observations on lead time¶

Observations on arrival year¶

Observations on arrival month¶

Observations on market segment type¶

Observations on repeated guest¶

Observations on repeated guest¶

Observations on number of previous booking not canceled¶

Observations on average price per room¶

Observations on number of special requests¶

Observations on booking status¶

Bivariate Analysis¶

Correlation¶

Booking Status vs Number of Adults¶

Booking Status vs Number of Children¶

Booking Status vs Number of Weekend Nights¶

Booking Status vs Number of Week Nights¶

Booking Status vs type of meal plan¶

Booking Status vs Required car parking space¶

Booking Status vs Room Type Reserved¶

Booking Status vs Arrival year¶

Booking Status vs Arrival month¶

Booking Status vs Market Segment Type¶

Booking Status vs Repeated Guest¶

Booking Status vs Number of Previous Cancellations¶

Booking Status vs Number of Previous bookings not cancelled¶

Booking Status vs No. of Special requests¶

Question 1: What are the busiest months in the hotel?¶

Question 2: Which market segment do most of the guests come from?¶

Question 3: Hotel rates are dynamic and change according to demand and customer demographics. What are the differences in room prices in different market segments?¶

Question 4: What percentage of bookings are cancelled?¶

Question 5: Repeating guests are the guests who stay in the hotel often and are important to brand equity. What percentage of repeating guests cancel?¶

Question 6: Many guests have special requirements when booking a hotel room. Do these requirements affect booking cancellation?¶

Data Preprocessing¶

Missing value treatement¶

Outlier Check¶

Model Building¶

Building a Logistic Regression model¶

Checking Multicollinearity¶

Converting coefficients to odds¶

Model performance evaluation¶

ROC-AUC¶

Optimal threshold using AUC-ROC curve¶

Using the Precision-Recall curve to see if we can find a better threshold¶

Final Model Summary¶

Building a Decision Tree model¶

Functions to calculate different metrics and confusion matrix so that we don't have to use the same code repeatedly for each model.¶

Building Decision Tree Model¶

Checking model performance on training set¶

Checking model performance on test set¶

Do we need to prune the tree?¶

Checking performance on training set¶

Checking performance on test set¶

Visualizing the Decision Tree¶

F1 Score vs alpha for training and testing sets¶

Checking performance on training set¶

Checking performance on test set¶

Model Performance Comparison and Conclusions¶

Actionable Insights and Recommendations¶

Actionable Insights¶

Recommendations¶